Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 10829
    Prev
    Next
    INDEX
    Explanations

    words related to visual descriptions, architecture, and artistic elements

    oai_token-act-pair · gpt-3.5-turbo

    elements related to urban environments and their transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    needs
    -0.70
     STATS
    -0.67
    DEP
    -0.66
     DOES
    -0.66
     Prediction
    -0.65
     Needs
    -0.63
    Lear
    -0.63
     Decision
    -0.62
    inventoryQuantity
    -0.61
    mits
    -0.61
    POSITIVE LOGITS
     abound
    1.81
     emerge
    1.44
     await
    1.44
     circulate
    1.42
     accompany
    1.36
     populate
    1.36
     illuminate
    1.30
     roam
    1.27
     dominate
    1.24
     haunt
    1.24
    Activations Density 0.296%

    No Known Activations